© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4768
    Prev
    Next
    INDEX
    Explanations

    quoted or parenthesized text starts

    np_acts-logits-general · gemini-2.5-flash-lite

    bullet points or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     heterogeneity
    0.25
     parameter
    0.25
     শিক্ষার্থী
    0.25
    係る
    0.24
     ಅನುಪಾತ
    0.24
     UnwrapRef
    0.24
     hindrance
    0.24
     \}
    0.24
     variables
    0.23
     decrement
    0.23
    POSITIVE LOGITS
     famously
    0.29
    which
    0.28
     infamous
    0.26
     ‘
    0.26
     badass
    0.26
     “‘
    0.25
    <em>
    0.25
    Cinema
    0.25
     famoso
    0.25
     pueblo
    0.25
    Activations Density 0.390%

    No Known Activations